Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Tank meta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Universit
    0.47
    ண்ட
    0.45
    treatment
    0.44
     hvil
    0.42
    throp
    0.42
     behand
    0.41
     \}
    0.41
    tem
    0.41
     Treatment
    0.41
     Behandlung
    0.40
    POSITIVE LOGITS
    ሖ
    0.52
     timezone
    0.50
    ה
    0.49
    лесо
    0.48
     overdraft
    0.48
     vacancies
    0.47
     heartwarming
    0.46
     caravans
    0.46
     toNumber
    0.45
     новое
    0.44
    Act Density 0.000%

    No Known Activations